A structural similarity based image fusion algorithm for night vision applications

Multi-sensor Night vision systems are playing their crucial role in modern warfare. Image fusion provides a way to merge such multi-sensor night-time imagery by combining the outputs of different imaging sensors in a consequent manner. In this paper, we present an optimized image fusion approach comprising Structural Similarity, Kernel Principle Component Analysis and Discrete Wavelet Transform. The use of structural similarity is proposed for adjusting the quality of finally fused image. Recently developed objective image fusion quality evaluation technique, image quality index, is used to evaluate the performance of our fusion algorithm. Experimental results show that it outperforms previous methods and performs considerably well across a variety of multisource night-time imagery.